KR20220108648A - System for providing non face-to-face online interview platform service - Google Patents

Abstract

Provided is a system for providing an untact online interview service comprising: a job-seeking terminal; a hiring terminal; and an interview service providing server. The job-seeking terminal uploads job-seeking information including academic background and career information; sets an untact interview schedule when receiving job matching; and performs mutual evaluation after an interview in an active chat window during an untact interview schedule time. The hiring terminal uploads hiring information including work, salary, a place or work, a corporate level, and treatment; selects whether to conduct an untact interview when receiving the job matching; activating the chat window during the untact interview schedule time when conducting the untact interview; and performs the mutual evaluation after the interview. The interview service providing server includes: an extracting unit which receives the job-seeking information and the hiring information from the job-seeking terminal and the hiring terminal; a schedule managing unit which allows the job-seeking terminal and the hiring terminal matched with keyword matching to set the untact interview schedule after performing the keyword matching based on a keyword; a chat managing unit which activates the chat window in the job-seeking terminal and the hiring terminal when setting the untact interview schedule; and an interview evaluating unit which performs the mutual evaluation with the job-seeking terminal and the hiring terminal. The present invention can improve efficiency of recruitment.

Description

Non-face-to-face online interview service provision system {SYSTEM FOR PROVIDING NON FACE-TO-FACE ONLINE INTERVIEW PLATFORM SERVICE}

The present invention relates to a system for providing a non-face-to-face online interview service, and provides a platform that can match job seekers in the right place through keyword weighting and keyword matching and can conduct an interview through text non-face-to-face.

Although job competency-oriented recruitment, represented by blind recruitment, is spreading recently led by the government, online job portals that still adopt document-based recruitment processes such as resumes and cover letters are leading the human resource recruitment market. If, in the past, the role of widely marketing job advertisements to induce the interest of potential applicants was important for recruiting managers of companies to discover excellent talents, now, among the many applicants received after posting the job advertisements, the role of marketing is important. The role of filtering unsuitable or non-qualifying applicants is becoming increasingly important. In a survey of job seekers and hiring managers, most of the interviews were selected as a reasonable recruitment evaluation standard and process when blind recruitment was applied. It suggests that the more accelerated, the greater the importance of the interview.

At this time, a method for conducting an online interview was researched and developed. August 13th), after receiving the question information from the service server, the job seeker terminal that transmits the video data of the interview video including the answer, collects the condition information of the talent you want to hire, and satisfies the condition information A configuration that tracks the past and present disclosed information of job seekers to determine the continuity and relevance of related work and delivers the results to the interviewer. Each configuration is disclosed so that the history information can be obtained more accurately and the job seeker can easily inform the job seeker himself.

However, the traditional interview method currently applied by most recruiting companies is different depending on the interviewer's point of view due to the evaluation that relies on subjective judgments such as routine and fragmentary conversations, impressions, and the influence of other external factors, such as appearance, rather than job-related validity. There is a strong tendency for evaluation to be made, and there is a tendency for fairness and reliability of recruitment to be lowered. In addition, if the document screening conducted before the interview is also full of the first-class information stipulated by the Personal Information Protection Act, including the resident registration number, but the personnel manager fails to properly dispose of it after reviewing it. is occurring Moreover, face-to-face interviews are no longer the direction to be headed in the post-coronavirus era. Accordingly, research and development of a platform that can conduct non-face-to-face interviews to enhance transparency and fairness in recruitment while increasing the matching rate among job seekers while protecting personal information is required.

An embodiment of the present invention builds a non-face-to-face interview platform for verifying job-seekers' basic job ability and job performance ability, and provides an evaluation function that can share scoring and evaluation opinions for each interviewer in order to enhance transparency and fairness of recruitment in the hiring solution. In order to increase the accuracy of matching, weighted keywords are used, and after matching, access is possible for a limited time only to those who have been requested for approval for personal information protection, and after that, the file cannot be viewed any more. The deletion process is performed within the server, and when the resume is viewed, the PC or mobile of the viewer is virtualized to prevent the intentional misuse of personal information. By introducing it, it is possible to provide a method of providing a non-face-to-face online interview service that can prevent job seekers from committing illegal acts to job seekers. However, the technical task to be achieved by the present embodiment is not limited to the above-described technical task, and other technical tasks may exist.

As a technical means for achieving the above-described technical task, an embodiment of the present invention uploads job search information including academic background and career information, sets a non-face-to-face interview schedule when receiving a job search match, and sets a non-face-to-face interview If you upload job information including job search terminal, job, salary, work location, company level, and treatment for mutual evaluation after conducting an interview in the chat window activated at the scheduled time, and receiving job matching, non-face-to-face interview In the case of non-face-to-face interview, the chat window is activated at the non-face-to-face interview schedule time, and after the interview is conducted, job search information and job search information are obtained from the job offer terminal and the job search terminal and the job offer terminal. An extractor that extracts keywords by uploading information, a schedule management unit that performs keyword matching based on the keyword, and sets a non-face-to-face interview schedule with the job search terminal and job search terminal matched by keyword matching, and the non-face-to-face interview schedule is set In this case, it includes an interview service providing server including a chat management unit to activate the chat window in the job search terminal and the job search terminal, and an interview evaluation unit to conduct mutual evaluation with the job search terminal and the job search terminal.

According to any one of the problem solving means of the present invention described above, it is possible to build a non-face-to-face interview platform for verifying job seekers' basic job skills and job performance ability, and to share scoring and evaluation opinions by interviewers to enhance transparency and fairness of recruitment The evaluation function is reflected in the recruitment solution, weighted keywords are used to increase the accuracy of matching, and after matching, access is possible for a limited time only to those who have been requested for approval to protect personal information. Deletion processing is performed within the server so that it can no longer be viewed, and when viewing resumes, the PC or mobile of the reader is virtualized to prevent intentional misuse of personal information. By introducing a mutual evaluation system for evaluation, it is possible to prevent job seekers from committing illegal acts against job seekers in the so-called position of A, and, ultimately, to enhance efficiency, transparency and fairness in recruitment.

1 is a view for explaining a system for providing a non-face-to-face online interview service according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating an interview service providing server included in the system of FIG. 1 .
3 and 4 are diagrams for explaining an embodiment in which a non-face-to-face online interview service according to an embodiment of the present invention is implemented.
5 is a flowchart illustrating a method of providing a non-face-to-face online interview service according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily carry out the present invention. However, the present invention may be embodied in several different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is "connected" with another part, this includes not only the case of being "directly connected" but also the case of being "electrically connected" with another element interposed therebetween. . Also, when a part "includes" a certain component, it means that other components may be further included, rather than excluding other components, unless otherwise stated, and one or more other features However, it is to be understood that the existence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded in advance.

The terms "about," "substantially," and the like, to the extent used throughout the specification are used in or close to the numerical values when manufacturing and material tolerances inherent in the stated meaning are presented, and are intended to enhance the understanding of the present invention. To help, precise or absolute figures are used to prevent unfair use by unscrupulous infringers of the stated disclosure. As used throughout the specification of the present invention, the term "step of (to)" or "step of" does not mean "step for".

In this specification, a "part" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. In addition, one unit may be implemented using two or more hardware, and two or more units may be implemented by one hardware. Meanwhile, '~ unit' is not limited to software or hardware, and '~ unit' may be configured to be in an addressable storage medium or may be configured to reproduce one or more processors. Thus, as an example, '~' denotes components such as software components, object-oriented software components, class components, and task components, and processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays and variables. The functions provided in the components and '~ units' may be combined into a smaller number of components and '~ units' or further separated into additional components and '~ units'. In addition, components and '~ units' may be implemented to play one or more CPUs in a device or secure multimedia card.

In this specification, some of the operations or functions described as being performed by the terminal, apparatus, or device may be performed instead of in a server connected to the terminal, apparatus, or device. Similarly, some of the operations or functions described as being performed by the server may also be performed in a terminal, apparatus, or device connected to the server.

In this specification, some of the operations or functions described as mapping or matching with the terminal means mapping or matching the terminal's unique number or personal identification information, which is the identification data of the terminal. can be interpreted as

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

1 is a view for explaining a system for providing a non-face-to-face online interview service according to an embodiment of the present invention. Referring to FIG. 1 , the non-face-to-face online interview service providing system 1 may include at least one job search terminal 100 , an interview service providing server 300 , and at least one job search terminal 400 . However, since the non-face-to-face online interview service providing system 1 of FIG. 1 is only an embodiment of the present invention, the present invention is not limitedly interpreted through FIG. 1 .

At this time, each component of FIG. 1 is generally connected through a network (Network, 200). For example, as shown in FIG. 1 , at least one job search terminal 100 may be connected to the interview service providing server 300 through the network 200 . In addition, the interview service providing server 300 may be connected to at least one job search terminal 100 and at least one job search terminal 400 through the network 200 . In addition, the at least one recruitment terminal 400 may be connected to the interview service providing server 300 through the network 200 .

Here, the network refers to a connection structure in which information exchange is possible between each node, such as a plurality of terminals and servers, and an example of such a network includes a local area network (LAN), a wide area network (WAN: Wide Area Network), the Internet (WWW: World Wide Web), wired and wireless data communication networks, telephone networks, wired and wireless television networks, and the like. Examples of wireless data communication networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), 5th Generation Partnership Project (5GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), Wi-Fi (Wi-Fi) , Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth (Bluetooth) network, NFC ( Near-Field Communication) networks, satellite broadcast networks, analog broadcast networks, Digital Multimedia Broadcasting (DMB) networks, and the like are included, but are not limited thereto.

In the following, the term at least one is defined as a term including the singular and the plural, and even if at least one term does not exist, each component may exist in the singular or plural, and may mean the singular or plural. it will be self-evident In addition, that each component is provided in singular or plural may be changed according to embodiments.

At least one job search terminal 100, after registering as a member using a non-face-to-face online interview service related web page, app page, program or application, enters job search information and approves access to the job search information of the job search terminal 400 It may be a terminal of a job seeker who selects the option of disclosing job search information by selecting whether to do or reject, active or inactive. And, the job search terminal 100 may be a terminal that selects whether or not to connect when keyword matching is made and then transmits an expression of intention to the interview service providing server 300 It may be a terminal that receives text input through an interview chat window after being selected. In addition, the job search terminal 100 may be a terminal that inputs the evaluation of the person in charge who makes the job offer to the interview service providing server 300 after the interview is finished, and the interview service providing server for the subsequent recruitment process or procedure It may be a terminal receiving guidance from 300 .

Here, the at least one job search terminal 100 may be implemented as a computer that can connect to a remote server or terminal through a network. Here, the computer may include, for example, navigation, a laptop equipped with a web browser, a desktop, and a laptop. In this case, the at least one job search terminal 100 may be implemented as a terminal that can connect to a remote server or terminal through a network. At least one job search terminal 100 is, for example, as a wireless communication device that guarantees portability and mobility, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS(Personal Handyphone System), PDA(Personal Digital Assistant), IMT(International Mobile Telecommunication)-2000, CDMA(Code Division Multiple Access)-2000, W-CDMA(W-Code Division Multiple Access), Wibro(Wireless Broadband Internet) ) terminal, a smartphone, a smart pad, a tablet PC, etc. may include all kinds of handheld-based wireless communication devices.

The interview service providing server 300 may be a server that provides a non-face-to-face online interview service web page, an app page, a program, or an application. In addition, the interview service providing server 300 may be a server that receives job search information and job information and extracts keywords after registering as a member in the job search terminal 100 and the job search terminal 400 . In addition, the interview service providing server 300 receives the keyword to be weighted among the extracted keywords from the job search terminal 100 and the job search terminal 400, performs matching between the weighted keywords, and returns the matched keyword. It may be a server that matches the job search terminal 100 and the job search terminal 400 that have submitted the extracted job search information and job information. Then, the interview service providing server 300 requests a response as to whether to connect to the job search terminal 400, and when a connection request event occurs, selects an interview schedule with the job search terminal 100, and after being selected, the interview schedule When this is confirmed, it may be a server that delivers the confirmed schedule to the job search terminal 100 and the job search terminal 400 . In addition, the interview service providing server 300 may be a server that activates the interview chat window and performs mutual evaluation with the job search terminal 100 and the job search terminal 400 when the interview is finished. The interview service providing server 300 may be a server that guides the interview result to the job search terminal 100 when it receives the interview result from the job search terminal 400 .

Here, the interview service providing server 300 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, navigation, a laptop equipped with a web browser, a desktop, and a laptop.

The at least one recruiting terminal 400 may be a terminal of a recruiter using a non-face-to-face online interview service related web page, an app page, a program, or an application. In this case, the job search terminal 400 may be a terminal that uploads job search information such as a job position, job type, trade name, address, and annual salary, and matches the job search terminal 100 with the interview service providing server 300 . Then, the job search terminal 400 allows access to the interview schedule from the interview service providing server 300 when selecting a matched job seeker, and selects the interview schedule, that is, the interview date and time from the job search terminal 100 In this case, it may be a terminal that receives the confirmed interview schedule from the interview service providing server 300 . In addition, the job search terminal 400 may be a terminal in which the interview chat window is activated according to the interview schedule, and when the interview is finished, the evaluation of the job seeker is inputted to the interview service providing server 300 . In addition, the job search terminal 400 may be a terminal that delivers the interview result to the interview service providing server 300 .

Here, the at least one recruitment terminal 400 may be implemented as a computer that can connect to a remote server or terminal through a network. Here, the computer may include, for example, navigation, a laptop equipped with a web browser, a desktop, and a laptop. In this case, the at least one recruiting terminal 400 may be implemented as a terminal capable of accessing a remote server or terminal through a network. The at least one recruitment terminal 400 is, for example, a wireless communication device that ensures portability and mobility, including navigation, Personal Communication System (PCS), Global System for Mobile communications (GSM), Personal Digital Cellular (PDC), PHS(Personal Handyphone System), PDA(Personal Digital Assistant), IMT(International Mobile Telecommunication)-2000, CDMA(Code Division Multiple Access)-2000, W-CDMA(W-Code Division Multiple Access), Wibro(Wireless Broadband Internet) ) terminal, a smartphone, a smart pad, a tablet PC, etc. may include all kinds of handheld-based wireless communication devices.

2 is a block diagram for explaining an interview service providing server included in the system of FIG. 1, and FIGS. 3 and 4 describe an embodiment in which a non-face-to-face online interview service is implemented according to an embodiment of the present invention. It is a drawing for

Referring to FIG. 2 , the interview service providing server 300 includes an extraction unit 310 , a schedule management unit 320 , a chatting management unit 330 , an interview evaluation unit 340 , a viewing management unit 350 , and a disclosure management unit 360 . ) may be included.

The interview service providing server 300 according to an embodiment of the present invention or another server (not shown) operating in conjunction with at least one job search terminal 100 and at least one job search terminal 400 provides a non-face-to-face online interview service When transmitting an application, program, app page, web page, etc., at least one job search terminal 100 and at least one job search terminal 400 are non-face-to-face online interview service applications, programs, app pages, web pages, etc. can be installed or opened. In addition, the service program may be driven in at least one job search terminal 100 and at least one job search terminal 400 by using a script executed in a web browser. Here, the web browser is a program that enables the use of a web (WWW: World Wide Web) service, and refers to a program that receives and displays hypertext written in HTML (Hyper Text Mark-up Language), for example, Netscape. , Explorer, Chrome, and the like. In addition, the application means an application on the terminal, for example, includes an app (App) executed in a mobile terminal (smartphone).

In the current Korean job market, the difference between job seekers and job seekers is a mixture of too many complex factors to be interpreted simply as an imbalance between supply and demand. The view that the Korean government's employment support-related policies are controversial in terms of quality as they were supplied focusing only on the quantitative expansion of the workplace rather than on qualitative core characteristics such as changes in employment qualifications. Accordingly, in recent years, the government has proposed major requirements for policies that provide opportunities for active participation in corporate jobs and various motives, but still, the government's employment policy roadmap does not include policies for alleviating the imbalance between job seekers and job seekers. There is a point of view that appears to be insufficient. In other words, we still adhere to the method of increasing the number of jobs quantitatively, but we need to look at it from the point of view that there is still a mismatch in perception between job seekers and job seekers that has not been resolved in the existing job market area. Rather, it raises the need to analyze the overall recruitment qualification evaluation trend at the present time.

In an embodiment of the present invention, when connecting with a company seeking job seekers, weight is given to keywords and keywords are matched. At this time, because there is a difference in perception between job seekers and job seekers, when job seekers give item weights to keywords A, B, and C, for example, but the hiring manager gives item weights to keywords D, E, and F, mutual matching This cannot be done properly. For example, if the job seeker puts weight on the career item by giving importance to the career, but the hiring manager gives weight to the academic background item, the matching cannot be done properly due to the difference in perception between the two sides, which is also a problem for the reliability of the platform of the present invention may occur. Accordingly, an embodiment of the present invention may establish a database for which items should be weighted for each job type or industry so that the recognition difference between the job seeker and the job seeker can be revealed and matching can be performed properly.

To this end, an embodiment of the present invention can be used for data analysis by collecting cases of job seekers and job seekers centered on job seekers. During the analysis process, only data with valid responses can be extracted and applied to the final analysis.

<Keyword visualization analysis>

In the process of detailed analysis techniques, word cloud analyzes the frequency tendency by reflecting all data of the text itself as it is, and human intervention may be required to correct typos or word separators that must be unavoidably performed due to the nature of the data. In addition, the related word analysis reflects all the data of the text itself as it is, analyzes the frequency trend of the connection between words in the same reaction unit (Case or Reference), and the final mined Word Cloud analysis data can be used as it is.

<Social Network Analysis>

In Social Network Analysis, the text is secondarily coded to analyze the frequency tendency of the connectivity between derived concepts within the same response unit (Case or Reference), and the data transformed with the 2-mode analysis frame are used for cluster analysis. 1-mode data can be analyzed by association. In particular, the concept of centrality can be derived from the analysis of associations, and centrality can focus on revealing who is at the center and who is at the edge of the group within the network. Therefore, centrality can be seen as the influence that one actor has on the entire network. Centrality has been developed in various ways, and it can be used for analysis by reflecting the characteristics of the degree of connection of the most general concept.

Degree of connection refers to the degree of connection with other nodes, and refers to the sum of other nodes connected to one node in the network. Actors with a high degree of connection play a key role in the network, and because they have relationships with other actors, they are more likely to obtain desired information and have greater power.

<Analysis of variance>

It is a way of resolving the debate about the possibility of population explanation of analysis in social sciences, and connecting qualitative big data type data to the stage of randomization analysis will provide a major scientific basis in academia. However, until recently, there have been very few cases in which this method has been applied, so for the application of analysis through parametric statistics, the frequency is calculated by focusing on the ANOVA design, and an analysis technique suitable for parametric statistics can be used based on this value.

The overall analysis can be performed step by step with Text Essential Variance Analysis (TEVA), and first, keyword visualization analysis can use the Word Cloud technique and Nvivo 12 Pro, which is suitable for the analysis of text itself. Second, for social network analysis, 1-mode correlation analysis was performed for each of the three types of comparison target classifiers using secondary data mined as quantitative data, and cluster analysis can be performed in 2-mode. Third, Gap Analysis utilizes secondary data mined as quantitative data to derive tertiary data clustered by three types of comparison target classifiers, and can perform 2-way ANOVA.

First, the keywords that are judged as hiring qualification areas and finally extracted are Major, Certificate, Academic Ability, Career, English, Foreign Language, Grades, Computer, preference, education, and external activities are extracted into a total of 11, but is not limited thereto.

<Comparison of large companies/small companies>

As a result of comparative analysis of the difference between large companies and SMEs by company size in terms of recruitment qualifications through keyword analysis, both large companies and SMEs place importance on academic background and career the most, but relatively large companies value academic background and SMEs place importance on career. . As a result of analyzing related words between large companies and SMEs for recruitment qualifications through related language analysis, both large companies and SMEs evaluate career, academic background, and professionalism as important. On the other hand, while large corporations regard career as relatively important, SMEs place importance on major. As a result of cluster analysis between large companies and SMEs for recruitment qualifications, education, academic background, foreign language, and preferential treatment were important for large companies, and English extracurricular activities, certifications, and computers were evaluated as important for small and medium-sized enterprises.

<Comparison of job seekers / job seekers in the manufacturing industry>

As a result of comparative analysis of the difference between recruiting companies and job seekers in the manufacturing industry with respect to hiring qualifications by keyword analysis, job seekers place importance on academic background and career, but job seekers value external activities, majors, and education. As a result of analyzing the related words of job seekers and job-seekers in the manufacturing industry for hiring qualifications, there are many differences in the factors that the two groups evaluate. As a result of cluster analysis between recruiting companies and job seekers in the manufacturing industry for recruitment qualifications, manufacturing job seekers place importance on English, computer, certification, and external activities, while manufacturing job seekers place importance on education, foreign languages, preferential treatment, and academic background.

<Comparison of recruiting companies/job seekers in the service industry>

As a result of keyword analysis of the difference between job seekers and job seekers in the service industry regarding recruitment qualifications, job seekers place importance on academic background and experience, but job seekers place importance on majors, qualifications, and education. As a result of analyzing the related words of job-seekers and job-seekers in the service industry for recruitment qualifications, there are many differences in the factors that the two groups evaluate as important. give importance to As a result of cluster analysis between recruiting companies and job seekers in the service industry regarding recruitment qualifications, service industry job seekers place importance on English, qualifications, computers, and external activities, while service industry job seekers place importance on academic background, foreign language, preferential treatment, and education.

Accordingly, a weight may be automatically set to an item corresponding to the above-mentioned importance depending on whether the company to which the job posting terminal 400 in charge of job recruitment belongs is a large company or a small and medium-sized business, and whether the type of business is a manufacturing or a service industry. In the end, this discrepancy in recognition in hiring qualifications appears because the recruiting company restricts specific information related to hiring or discloses only too general information. it can be solved However, since the company does not disclose information such as educational background or career, job seekers are only guessing the company's talents by looking at the specifications of those who have passed. Accordingly, in the case of constructing big data by collecting data of people who have passed each recruitment, it is not difficult to extract information such as educational background, career, foreign language level, and qualifications desired by each company. In addition, since it can tell you exactly how many specifications you need to prepare to go to which company, it can give no room for random application or recruitment corruption where a so-called parachute is stuck in each department. In addition, by giving weight to each item, the personnel manager can automatically extract and match applicants who maintain good specifications for the item they want, thereby saving the hiring cost of the headhunter and the time of the personnel manager.

Of course, as will be described later, setting the keyword weight in the job search terminal 100 is to set the keyword weight according to how accurately the job type is matched, which is a separate concept from the above-described item weight. The above-mentioned item weight is a weight for an important item between the job seeker and the job seeker, and setting the weight in the job search terminal 100 is a weight for how closely the keyword is related to the job the job seeker wants to find. That is, in the latter case, for example, if "accounting" is described in the career of job search information, related business words such as financial accounting, management accounting, settlement of accounts, and payment are extracted, and the job seeker is most likely to It is to assign a percentage of weights in the order of relevance. If you have done most of the settlement work, give 50% weight to settlement of accounts, 30% to financial accounting if you have done the next most financial accounting, and 20% to management accounting if you have done a little bit of management accounting. to find information.

The components of FIG. 2 will be described below on the premise of the above-mentioned item weights.

The extraction unit 310 may extract keywords by uploading job search information and job information from the job search terminal 100 and the job search terminal 400 . The job search terminal 100 may upload job search information including academic background and career information. Recruitment terminal 400 may upload job information including job, annual salary, place of work, company level, and treatment. Keyword matching may be based on at least one artificial intelligence algorithm. Keyword matching extracts words with high similarity to the pre-established work-related word dictionary from career information included in job search information, sets them as keywords, searches for work-related words based on the keywords, and then extracts keywords and work-related words to the job search terminal 100, the job search terminal 100 selects a work keyword among keywords and work-related words, and requests to input a weight to the work keyword so that the keyword matching is weighted and executed.

<Extract keywords>

In this case, when extracting the keyword, TF-IDF (Term Frequency-Inverse Document Frequency) may be used. TF-IDF is a statistical technology that is used in information retrieval and text mining fields and indicates how important a word is within a specific document in various documents. It is used to extract keywords, determine the ranking of search results, and measure the similarity of documents. TF represents the word frequency and represents how many times a word appears in a document, IDF represents the reciprocal of the DF value, and DF represents how many times a word appears in a document set.

TF can basically be calculated using the total frequency of words in a document, but this method has a problem in that the value continuously increases when the document is large or the number of words increases. Three methods can be defined as a method for improving the size problem. First, the frequency of calling is defined as 0 and 1 as TF values based only on the appearance of words. Second, the log scale frequency can reflect the size problem and the actual frequency by taking the logarithm of the TF value. Finally, the increment frequency does not exceed one on a maximum scale in such a way that it represents the relative frequency of words along the length of the document. IDF is calculated by dividing the total number of documents by the number of documents containing the word and taking the logarithm. The TF-IDF is higher as a word has a higher frequency within a specific document and there are fewer documents containing the word among all documents. This allows you to filter out words that appear frequently in all documents.

The vector space model is called a word space model in the text mining field and is an algebraic model representing a given text document as a vector of words. The vector space model is used for information filtering, information retrieval, indexing, and similarity ranking. When a word is included in the document, that word will have a non-zero vector value. There are several methods for calculating this value, called word weight, and the representative TF-IDF method is used.

Word embedding refers to a method of quantifying the words constituting the text. This methodology allows words to be represented in vector space. In the past, words were vectorized using a one-hot encoding method. One-hot encoding refers to expressing a specific word as a vector by creating a vector of size N in order to express a specific word when there are N dictionaries, putting 1 in the corresponding place of the word, and 0 in the remainder. Spam classifiers use this method. Currently, two types of methodologies exist and are divided into count-based methods and prediction-based methods. The count-based method uses frequencies such as count vectors and TF-IDF vectors. The prediction-based method applies a neural network model to predict the next word given a word or sentence, and the current Word2vec is This applies here. Word2vec performs word embedding using CBOW and Skip-Gram methods, CBOW (Continuous Bag of Words) lists several words and predicts related words, and Skip-Gram is a word that can be context from a specific word as opposed to CBOW. predict

KoNLPy is a Python-based Korean information processing package and open source software. This package provides functions such as simple term search, morphological analysis, and part-of-speech tagging. It can also be used with Python's visualization and text analysis packages rather than being used alone. Gensim is a deep learning package for vector space modeling and provides functions such as TF-IDF, LDA, and Word2vec. In the case of Word2vec, when this package is applied, it is said that the speed is 70 times faster than that implemented with Numpy. It supports efficient handling of large-scale text data through high speed.

<Keyword similarity>

When extracting the above-described similarity, the cosine similarity may be used. This means the degree of similarity between vectors measured using the cosine value of the angle between two vectors in the dot product space. When the angle is 0, the cosine value is 1 and all other angles are less than 1, so it is used for the purpose of judging the similarity of directions, not magnitudes of vectors. has Commonly, it is usefully used to measure the similarity between words, sentences, and document vectors in the fields of information retrieval and text mining. Cosine similarity is expressed as a scalar product and magnitude of vectors given A and B vector values.

<Business related words>

In order to provide a related word, a method of recommending a related word by first analyzing a log of a user or a search engine may be used. After extracting additional search words input by users together with the search word as a related word candidate group, from this candidate group It is a method of recommending words that have appropriate meaning in the content. It shows relatively high accuracy as many people and search engines can identify words that are actually related. However, the complexity of analyzing the log of the user and the difference in thoughts of each user have different preferred fields of interest, and the multiplicity of word meanings has limitations in obtaining the relevant word desired by the user.

Another method is to create a user profile and extract related words. When the user searches for a specific word, the user recommends related words by referring to a profile created with keywords related to the user's field of interest. However, in order to understand the user's area of interest, it is difficult to extract related words related to the user's area of interest in the early stage before the user's profile is created because it is necessary to observe the user's search pattern and write related information to the profile.

Accordingly, in an embodiment of the present invention, a word with high semantic relevance to a search word can be efficiently extracted by analyzing a large amount of data without biasing a specific user search by utilizing the big data processing technology. First, data including a search word may be collected, and morphological analysis may be performed through the collected data. The frequency is calculated through the MapReduce operation on the morpheme-analyzed data, and the data is stored according to the HBase schema configured for the data extracted from the data storage module. In order to automatically collect a large amount of data, the extracted words are excluded from already searched words, and then the extracted words are sent as search words to recursively collect data. In data extraction, HBase's filter function is used to obtain related words and related data for the word searched by the user.

First, after collecting relevant data, each content is divided into sentences to perform morphological analysis. When performing morpheme analysis, it is performed to extract only common nouns and proper nouns. After determining each part-of-speech, parts-of-speech such as articles, prepositions, surveys, and conjunctions that will be stop words are removed, and parts of speech that will become related word candidates are removed. Extract common nouns and proper nouns. In the frequency extraction module, the frequency of each word is calculated through the common noun and proper noun received from the morpheme analysis. After calculating the frequency of extracted words when a search word is input by performing a MapReduce operation, the secondary sort provided by Hadoop is used to sort in order of highest frequency.

When saving data, the previously extracted data is stored in HBase. When storing data in HBase, the search word is stored as a row key, the column family is divided, and the data is stored in the qualifier according to each column family. By specifying extracted_word in the first column family name, the word extracted through the search word is saved. In the second column family name, specify recent_url to store the Internet address where the related word appears, and in the third column family name to store the Internet creation date. In Value, the frequency of each extracted word is stored.

In order to automatically collect data on related words, a word extracted as a search word may be sent as a search word to collect data in a recursive manner. When collecting data recursively, if a word entered as a search word is stored as a low key in HBase, it is set to skip without collecting Internet data to prevent data duplication. When collecting data recursively, data can be collected by limiting the maximum number of search steps so as not to fall into an infinite loop.

When extracting data, related words and related data can be extracted through the filters for raw, qualifier, and value provided by HBase. After the user searches for the word to be searched with the RowFilter, the top N words with high relevance are found using the ValueFilter, and the relevance of the search word and the related word is measured by modifying the TF (Term Frequency). do.

Equation 1 represents a method of calculating the association of the extracted word We by the user setting the first time point Ps and the last time point Pe for the search word Ws. Frequency is the frequency of words extracted at a specific point in time (P), and Pe-Ps is the number of days in a user-specified period. After calculating the average value using the frequency of extracted words extracted through the search word during the period specified by the user, the correlation between the search word and the extracted word is calculated. After searching the top N data with high relevance with the value filter, each extracted_word, recent_url, and day can be found using a QualifierFilter and provided to the user along with the related word.

In order to check the accuracy of the technique of extracting the related words after providing the related words and before constructing the dictionary, feedback from users (job seekers, job seekers) is required. Of course, experiments can also be performed, and performance evaluations can also be performed using NDCG (Normalized Discounted Cumulative Gain).

Equation 2 is an expression showing a method of calculating the NDCG, and indicates the degree of relevance (ni = 1,2,3,4,5) in the p-th search result. ni is a number that measures the degree of relevance between the search word and the related word in the experiment. Relevance can also be shown. Zn is a normalized constant that is calculated so that the value of NDCG becomes 1 when the most appropriate search result is obtained.

The schedule manager 320 may set a non-face-to-face interview schedule with the job search terminal 100 and the job search terminal 400 matched by keyword matching after performing keyword matching based on the keyword. The job search terminal 100 may set a non-face-to-face interview schedule when receiving job search matching. Recruitment terminal 400 may select whether to proceed with a non-face-to-face interview when receiving a job search match. The schedule management unit 320, if you want to conduct a non-face-to-face interview in the job search terminal 400, checks the interview schedule of the job search terminal 400, extracts the date and time available for the interview, and transmits it to the job search terminal 100 And, the interview schedule can be confirmed with any one date and time selected by the job search terminal 100 and transmitted to the job search terminal 400 and the job search terminal 100 .

The chat management unit 330 may activate a chat window in the job search terminal 100 and the job search terminal 400 when a non-face-to-face interview schedule is set. Recruitment terminal 400 may activate the chat window during the non-face-to-face interview schedule time when the non-face-to-face interview is conducted.

The interview evaluation unit 340 may perform a mutual evaluation with the job search terminal 100 and the job search terminal 400 . The job search terminal 100 may perform a mutual evaluation after conducting an interview in the chat window activated during the non-face-to-face interview schedule time. Recruitment terminal 400 may perform a mutual evaluation after conducting an interview. The interview evaluation unit 340, the job search terminal 100 and the job search terminal 400, and the evaluation of the received job search and job seekers are mapped to the job search terminal 100 and the job search terminal 400, respectively, so that the cumulative storage can be stored. .

The viewing management unit 350, when receiving the job search matching from the job search terminal 400, requests the approval of the reading of the job search information to the job search terminal 100, and when the reading approval is obtained from the job search terminal 100, the job search terminal ( 400) may allow you to view job search information. The viewing management unit 350, when receiving and outputting job search information from the job search terminal 400, executes Server Based Computing or Virtual Desktop Infrastructure to prevent personal information from being leaked do. In addition, the viewing management unit 350 may be set to allow access to the job search information only within a limited time by setting a time available for viewing the job search information in the job search terminal 400 .

The disclosure management unit 360 may select the information disclosure option of the job search information from the job search terminal 100 , and when the information disclosure option is selected from the job search terminal 100 , it may be mapped with the job search terminal 100 and stored. The information disclosure option is an approved open option that opens only when approved by the job search terminal 100, a fully open option that opens even if the job search terminal 100 does not approve, and does not open regardless of whether the job search terminal 100 is approved May include unopened options. At this time, since it is an online platform, there may be cases of cheating on academic background or career.

The block chain can be based on the pseudo code of the chain code, and the block chain network consists of a three-party structure of the public management unit 360 , the job search terminal 400 , and the job search terminal 100 . The public management unit 360 is a full node and has all the rights of the network, and the job search terminal 400 and the job search terminal 100 participate in the network with limited functions as a light weighted node.

<Block creation procedure>

Block generation is performed when participating in a blockchain network in the job search terminal 100 or changing the educational background and career of a job seeker. ① The job search terminal 100 participates in the block chain network as the public management unit 360 and requests block generation when registering its own information in the block chain and changing existing information. ② When the public management unit 360 receives a registration request, it starts a block generation procedure based on the information provided by the job search terminal 100 . At this time, it is searched whether the job seeker is registered in the block chain in order to check whether there has been a job seeker in the job search terminal 100 in the past. ③ According to the request of the manager terminal (not shown) in the public management unit 360, it is checked whether the job seeker is registered in the block chain, and it is transmitted to the manager. ④ The manager requests the government information about the job seeker's educational background and career in order to check whether the job seeker's information is forged. ⑤ The government checks whether it is acceptable to provide information about educational background and career to job seekers. ⑥ The job search terminal 100 transmits whether or not to consent to the provision of personal information so that its own information can be stored in the block chain. ⑦ The government communicates whether the job seeker information is verified. ⑧ Information about job seekers is created and stored as a block in the block chain.

<Individual academic background and career verification process>

The academic background and career provision procedure is used when a job seeker searches for a job, submits a resume, etc. to the recruitment terminal 400, such as a company, and is used as a request of the recruitment terminal 400 to check whether the contents of the resume are forged. can First, ① When an applicant who is registered as a job seeker submits a resume to the company's terminal, that is, the job search terminal 400, he/she submits his/her ID registered in the block chain together. ② The company receives the applicant's resume and notifies whether or not it has been received. ③ The company requests the disclosure management unit 360 to verify whether or not the applicant's academic background and career are forged. ④ The public management unit 360 confirms whether the applicant agrees to check the career in the block chain. ⑤ The applicant sends a message to the disclosure management unit 360 to give permission to inquire about his/her own data. ⑥ The public management unit 360 checks the internal data of the block chain by executing the chain code, and at this time, searches the job seeker data using the job seeker (applicant)'s unique ID. ⑦ The public management unit 360 transmits the data registered in the block chain to the company (the job offer company of the job offer terminal 400) so that it can be checked whether forgery or not.

<Chain code operation>

You can use the chaincode for consent to provide personal information, search for data inside the block, create and modify blocks, and verify career information. Since the career and educational background information of the job seeker is included in the personal information, a procedure to confirm whether the job seeker agrees to the information is necessary. The subject using the chaincode is used by the government, which can help verify job seeker information. In this case, the method of obtaining consent to provide information from the job seeker is to receive confirmation of consent in the form of a message or e-mail. Block generation and verification can be performed only when job seekers agree to provide information.

The chain code used to search for job seekers can be used after confirming consent to provide personal information. This is because it is a chaincode that actually gets the data inside the blockchain. Data search chaincode can be searched using two methods: QueryString and txType. The QueryString method is a method of performing a search using only the job seeker ID. The txType method is a method of performing a search by assigning a job seeker ID and additional conditions. At this time, if the corresponding chain code is not used, it may be configured so that information cannot be verified in the block chain.

The background technology used in the above configuration is blockchain, chaincode, and hyperledger consensus algorithm. First, blockchain is used to synchronize data to simplify complex systems or prevent confusion by utilizing blockchain. The difference between the existing security method and the blockchain is that by providing the same information to everyone involved in the network, even if a specific person forges data, it is not recognized because it is different from the information known to all members. In other words, it is a technology that performs anti-counterfeiting through disclosure, unlike the existing data hiding.

Transactions in the blockchain can only be registered in a block if they are authorized using a hash function. In this process, an electronic signature is used, which is used to provide a non-repudiation function. The method that is mainly used as a method for transaction processing is the method using chaincode. Chaincode is used not only to generate blocks, but also to provide functions that can provide various services using blockchain. Chaincodes can be classified into system chaincodes and user chaincodes.

Hyperledger Fabric uses a different transaction processing method than other blockchain platforms. In the case of other blockchain platforms, a method of linking with the chain is used by verifying the transaction contents. In contrast, Hyperledger Fabric operates with procedures of Execute, Order, Validate, and Update state. In the case of the existing Hyperledger Fabric, the PBFT (Practical Byzantine Fault Tolerance) method was used as a consensus method, but a decrease in transaction per second (tps) performance occurred as a problem. In this case, it may be applied using simple BFT (SBFT). Of course, since a license, academic background, or career may be verified or shared by various methods other than the above-described method, the present invention is not limited thereto.

If the number of occupations and personnel employed by a single company through the platform of the present invention is large, or if the occupations and personnel employed by the same similar company through the platform of the present invention are sufficiently accumulated to model the AI algorithm, the data If a DataSet is built, a dataset can be created like the input [Job information - Judgment result of the hiring company - Judgment reason], and when it is accumulated enough to learn the AI algorithm, a collaborative deep learning algorithm can be developed. It is automated while minimizing human intervention (person in charge), enabling faster and more accurate document screening.

First, information on applicants desired by the company is inputted in a preset format. It quantifies the talents and abilities of applicants through the advance prediction algorithm for applicant verification, and based on the quantified information, it is possible to provide and recommend optimal candidate candidate information to HR managers through a collaborative deep learning algorithm. Finally, for information visualization, the contents analyzed based on the applicant's profile information can be visualized as infographics and provided to the personnel manager.

<Collaborative Deep Learning-based Applicant Recommendation Algorithm>

We describe a collaborative deep learning-based applicant recommendation algorithm that can quantify to intuitively evaluate applicants’ talents/capabilities for applicant verification and recommend optimal applicants to HR managers by analyzing quantified data. The algorithm mainly operates in two parts. First, it is a pre-prediction algorithm for candidate validation. After normalizing the candidate's profile data, based on the normalized profile data, the root node and the leaf node are It creates a decision tree containing Based on the generated rules, numerical data about the talents and abilities of applicants are extracted. The pre-prediction algorithm first computes the entropy coefficient for each variable in the data in the normalized profile.

The information gain for each variable of the normalized profile data allows data to be classified into specific data properties, and the average value of the entropy weight of the lower node derived from the entropy coefficient for each variable of the profile data (expected information) Calculate by finding the difference of Second, a collaborative deep learning algorithm is performed based on the extracted quantified talent/ability data. Collaborative deep learning is suitable for collaborative filtering, which is most commonly used in recommendation technology, K-NN algorithm for user similarity analysis, and matrix-type dataset analysis. It may be a recommendation algorithm mixed with RNN (Recurrent Neural Network), which is a deep learning algorithm.

The quantified talent and ability dataset U of the applicant is set as input data, and the predicted nth user U's optimized recruitment information (hat)hn and RNN_Rec_Listn are output data. First, define the activation function, Sigmoid, and the parameters required for RNN: alpha, input_dim(input dimensions), hidden_dim(hidden dimensions), output_dim(output dimensions), train_cir(train circle, training branch) number of times) can be defined. Next, we can initialize the weights and prepare to create our training model, chra_model. In RNN, in order to eliminate errors in model generation, forward propagation and back propagation can be basically performed.

Predicted optimized recruitment information is generated through the learned chra_model, and at this time, it is calculated based on analysis data for similar users through KNN clustering, and KNN clustering is calculated as shown in Equation 3 below.

Here, k is the number of clusters, and the difference between the two candidates xi and yi is calculated to calculate the similarity based on the distance. Finally, a recommendation list, RNN_Rec_Listn, is generated based on the predicted optimized candidate selection information and provided to the personnel manager.

In this case, in addition to infographics, a Cognostics-based analysis method may be used as a visual analysis method of multidimensional data. Cognostics-based analysis method is a method of calculating and scoring numerous visualizations that can be made through multidimensional data based on specific indicators, and then prioritizing visualization exploration based on the scores. The Cognostics method is meaningful in that it enables efficient analysis for data analysts in that it is possible to draw so many charts that it is difficult to look at them all due to the nature of multidimensional data.

Among the cognostics analysis methods, the method that mainly treats the scatter plot as an analysis target is called Scagnostics (Scatterplot + Diagnostics). A scatterplot is a representative visualization that connects two variables to the X-axis and Y-axis, respectively, so that the distribution of the two variables can be seen. If you want to analyze 20-dimensional data (10 variables or columns of data) using Scagnostics, 190 scatterplots, the number of cases in which 2 of 20 variables are selected, are the target. So, 190 scatterplots are calculated based on specific indicators, and when the scores and rankings corresponding to the results are obtained, you can check the scatterplots in ascending order or with a slightly unusual score distribution.

At this time, categorical variables are included in the Scagnostics analysis method, and at the same time, progressive visual analysis can be applied to the analysis to effectively handle the rapidly increasing number of scatter plots. After inclusion, when the scatterplot is divided into specific categories, the categories of the scatterplots with striking and interesting patterns can be identified. You can use the visualization and interaction methods it provides.

Hereinafter, an operation process according to the configuration of the interview service providing server of FIG. 2 will be described in detail with reference to FIGS. 3 and 4 as an example. However, it will be apparent that the embodiment is only one of various embodiments of the present invention and is not limited thereto.

<Member Registration>

First, if the platform according to an embodiment of the present invention is tentatively called a JobTalk room, in the member registration step of the JobTalk room platform, member registration is possible only by setting an ID and password or by simple mobile phone authentication. Job seekers must enter their name, gender, date of birth, place of residence, mobile phone number (ID) and authentication number, and the hiring manager must create a business name, address, industry type, business number (ID) and password. After agreeing to the use of personal information, in the stage of completing membership registration, menus such as platform promotion (how to use), recruitment success reviews, recruitment information and recruitment mentoring can be displayed, and membership registration, chat room opening, matching signal occurrence status, etc. are disclosed. In order to encourage members to sign up for membership and open a chat room.

<Register detailed member information>

In the next step, member detailed information, that is, data that is the basis for matching, must be registered. It is information that can be used for weighted keyword matching (artificial intelligence algorithm) to register the current detailed information. Job seekers can upload resumes, career descriptions, self-introductions, certifications, and personal promotional materials (photos of results, portfolios, blogs, etc.)

Information disclosure options may be given, and as described above, there are approved open (activity start), fully open (activity start), and non-open (activity suspension/suspend/inactivity) options. In addition to communication between job seekers and job seekers, communication between job seekers and job seekers and between job seekers and job seekers may also be possible. The basic structure of a chat room for job seekers and job seekers is shown in FIGS. 3A and 3B. And, the detailed information registration list may be as shown in Table 1 below.

Current details Hope (recruitment/employment) information job seeker job vacancies job seeker job vacancies Basic information (required) my resume Company information work Recruitment Guide career description Academic background (graduation/graduate) certificate promotional material Salary Question reservation (secret) self-introduction portfolio place of work Expected date of non-face-to-face interview certificate result photo Company level/treatment Individual notification of non-face-to-face interview results Etc blog Etc

Basic information (required) is an open principle and becomes keyword matching analysis data. It is possible to automatically search for keywords related to work experience, and multiple selections are possible. For example, when the word accounting is entered, the job-related automatic search words are financial accounting, management accounting, settlement of accounts, and payment, etc., and after extraction, the selected job keyword can be given a weight corresponding to the actual career job, e.g. For example, you can set up to 3 ranks. For example, it may be 1st rank settlement 50% > 2nd rank financial accounting 30% > 3rd rank management accounting 20%, and so on. Also, in the case of the annual salary, it may be a fixed current salary (including divisive allowance, severance pay, and performance-based pay), 5%, 10%, 15%, 20%, etc. At this time, since there are cases where even the current salary is deceived, it is also possible to request the health insurance premium data to be paid to the National Health Insurance Corporation, or to inquire or read through the above-mentioned block chain, and then have the salary calculated inversely.

<Request/approval/rejection of detailed information of job seekers/recruiters>

Referring to FIG. 4A , it is a screen for notifying a reading request and automatically guiding and selecting whether to approve or reject it.

<Occurrence of matching signal/non-face-to-face interview/confirmation of schedule>

Referring to FIG. 4B , a matching signal is transmitted to each party, and the schedule of each party is checked and selected in order to set a schedule as shown in FIG. 4C , and when it is confirmed, the party may be informed of the confirmed interview schedule.

<Non-face-to-face interview/Evaluation of etiquette/result sharing>

Referring to FIG. 4D , for example, a guide message is delivered 10 minutes before an interview, and when the interview is in progress, both parties' attendance is confirmed. In this case, if text is input late from either party, a penalty for the late time may be provided. For example, based on the number and time of being late, the tag "tardiness" and the number and time may be tagged together, or a penalty may be given in a manner that reduces the etiquette index. After the interview, a guide message is transmitted so that they can evaluate each other as shown in FIG. 4E, and the etiquette index of each party can be calculated using this. In addition, when the interview result is input from the hiring manager, it can be delivered to the job seeker to guide the result.

<Non-face-to-face interview AI result analysis>

When the person in charge of the hiring company schedules and registers a question for a non-face-to-face interview, if the person in charge sets the expected answer keyword in advance, after a non-face-to-face interview between [person in charge - job seeker], When the degree of similarity between answer keywords exceeds a preset reference value, a percentage of the degree of similarity may be extracted and the expected interview score may be notified to the job seeker in advance. In this case, it serves as an indicator for job seekers to assess their success before announcing the interview results. However, since the word system and vocabulary used by job seekers are all different, the degree of similarity may be somewhat lower even for words with the same meaning, unless the exact same word as the keyword set by the person in charge appears in advance. Accordingly, when a dictionary of related words, similar words, or synonyms is built using the established Sejong Corpus (Corpus), job seekers who say keywords that are not exactly the same as the keywords set by the person in charge but have the same meaning, are similar or related There may be grounds for giving a score to

However, if the AI interview result is different from that of the actual recruiting company, it may confuse job seekers and cause problems and complaints about the reliability of the recruitment system and the recruiting company. Accordingly, it may be implemented in a way of notifying the hiring company preferentially. For example, if there are many non-face-to-face job seekers, the job seekers with the highest AI interview results can be reviewed first by filtering out the hassle of the hiring manager checking the interview results one by one.

<Talent donation in the professional business area>

When a job seeker or a job seeker enters the information of the job seeker and the job seeker, respectively, it is possible to check whether talent donation is possible in the areas of professional work and strengths. If you create a talent donation category for professional work and use a filter, you can help small and medium-sized businesses or start-ups that have difficulty in recruiting professional manpower.

<Information Communication by Recruitment/Employment Subject>

You can create more channels or pages to share or communicate information between job seekers and job seekers, between job seekers and job seekers, and between job seekers and job seekers. In particular, although general recruitment sites, portal sites, and platforms do not communicate information between job seekers and job seekers, the platform according to an embodiment of the present invention enables information communication between job seekers as well. It is also possible to verify specifications and talents, and introduce talents (recruitment, relocation, etc.). For example, small and medium-sized enterprises (SMEs) can receive introductions of talented people with excellent experience from mid-sized companies or higher, and companies with a size larger than medium-sized companies can use it as a method of restructuring their internal workforce.

<One-to-many non-face-to-face interview>

When conducting a non-face-to-face interview, there are methods such as one-to-one, one-to-many, and many-to-many. can be transmitted.

The matters not described with respect to the non-face-to-face online interview service providing method of FIGS. 2 to 4 are the same as those described for the non-face-to-face online interview service providing method through FIG. 1 or can be easily inferred from the described content. Therefore, the description below will be omitted.

5 is a diagram illustrating a process in which data is transmitted/received between components included in the non-face-to-face online interview service providing system of FIG. 1 according to an embodiment of the present invention. Hereinafter, an example of a process in which data is transmitted/received between each component will be described with reference to FIG. 5, but the present application is not limited to such an embodiment, and the example shown in FIG. 5 according to the various embodiments described above will be described. It is apparent to those skilled in the art that the data transmission/reception process may be changed.

Referring to FIG. 5 , the interview service providing server extracts keywords by uploading job search information and job information from the job search terminal and the job search terminal (S5100).

Then, the interview service providing server, after performing keyword matching based on the keyword, sets a non-face-to-face interview schedule with the job search terminal and the job search terminal matched by keyword matching (S5200), and chatting when the non-face-to-face interview schedule is set Let the window be activated in the job search terminal and the job search terminal (S5300).

Finally, the interview service providing server, the job search terminal and the job search terminal to proceed with the mutual evaluation (S5400).

The order between the above-described steps ( S5100 to S5400 ) is merely an example and is not limited thereto. That is, the order between the above-described steps ( S5100 to S5400 ) may be mutually changed, and some of these steps may be simultaneously executed or deleted.

Matters not described for the non-face-to-face online interview service providing method of FIG. 5 are the same as those described for the non-face-to-face online interview service providing method through FIGS. 1 to 4 or can be easily inferred from the described content Therefore, the description below will be omitted.

The non-face-to-face online interview service providing method according to the embodiment described with reference to FIG. 5 may also be implemented in the form of a recording medium including instructions executable by a computer, such as an application or program module executed by a computer. . Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. Also, computer-readable media may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The non-face-to-face online interview service providing method according to an embodiment of the present invention described above may be executed by an application basically installed in a terminal (which may include a program included in a platform or an operating system basically installed in the terminal). Also, it may be executed by an application (ie, a program) directly installed in the master terminal by the user through an application providing server such as an application store server, an application, or a web server related to the corresponding service. In this sense, the non-face-to-face online interview service providing method according to an embodiment of the present invention described above is implemented as an application (ie, a program) installed by default in a terminal or directly installed by a user, and can be read by a computer such as a terminal. It can be recorded on a recording medium.

The foregoing description of the present invention is for illustration, and those of ordinary skill in the art to which the present invention pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a dispersed form, and likewise components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the following claims rather than the above detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention. do.

Claims (11)

A job search terminal that uploads job search information including academic background and career information, sets a non-face-to-face interview schedule when receiving a job search match, conducts an interview in an active chat window during the non-face-to-face interview schedule, and performs mutual evaluation ;
Upload job information including job, salary, place of work, company level and treatment, select whether to conduct a non-face-to-face interview when receiving a job search match, and select whether to proceed with the non-face-to-face interview Recruitment terminal for activating the chat window at a scheduled time and performing a mutual evaluation after conducting an interview; and
An extractor for extracting keywords by uploading the job search information and job information from the job search terminal and the job search terminal, and after performing keyword matching based on the keyword, a non-face-to-face interview with the job search terminal and the job search terminal matched by the keyword matching A schedule management unit to set a schedule, a chatting management unit to activate the chat window in the job search terminal and the job search terminal when the non-face-to-face interview schedule is set, and an interview evaluation unit to conduct mutual evaluation with the job search terminal and the job search terminal an interview service providing server;
Non-face-to-face online interview service providing system that includes.
The method of claim 1,
The interview service providing server,
When receiving the job search matching from the job search terminal, requesting approval for viewing the job search information to the job search terminal, and a viewing management unit for viewing the job search information in the job search terminal when viewing approval is obtained from the job search terminal;
Non-face-to-face online interview service providing system, characterized in that it further comprises.
3. The method of claim 2,
The reading management unit,
Non-face-to-face online interview service providing system, characterized in that when the job search information is received and output from the job search terminal, server-based computing or virtual desktop infrastructure is executed.
3. The method of claim 2,
The reading management unit,
Non-face-to-face online interview service providing system, characterized in that set to allow access only within a limited time by setting a time available for viewing the job search information in the recruitment terminal.
The method of claim 1,
The schedule management unit,
If you want to conduct a non-face-to-face interview in the job search terminal, check the interview schedule of the job search terminal, extract the available date and time for an interview, and transmit it to the job search terminal, any one date and time selected by the job search terminal Non-face-to-face online interview service providing system, characterized in that the interview schedule is confirmed and transmitted to the recruitment terminal and the job search terminal.
The method of claim 1,
The interview evaluation unit,
Non-face-to-face online interview service providing system, characterized in that the job search terminal and the evaluation of job seekers received from the job search terminal and the job search terminal are mapped to the job search terminal and the job search terminal, respectively, and accumulated and stored.
The method of claim 1,
The keyword matching is
After extracting a word with a high degree of similarity to a pre-established work-related word dictionary from the career information included in the job search information and setting it as a keyword, searching for work-related words based on the keyword, extracting the keywords and work-related words Non-face-to-face, characterized in that it is transmitted to the job search terminal, the job search terminal selects a work keyword from the keyword and the work-related word, and requests to input a weight to the work keyword, giving weight to the keyword matching Online interview service provision system.
The method of claim 1,
The interview service providing server,
a disclosure management unit for selecting the information disclosure option of the job search information from the job search terminal, and for storing the mapping with the job search terminal when the information disclosure option is selected from the job search terminal;
Non-face-to-face online interview service providing system, characterized in that it further comprises.
9. The method of claim 8,
The information disclosure option is
Non-open option that opens only when approved by the job search terminal, a fully open option that opens even if the job search terminal does not approve, and a non-open option that does not open regardless of whether the job search terminal is approved Face-to-face online interview service provision system.
The method of claim 1,
The non-face-to-face online interview service providing system, characterized in that the keyword matching is based on at least one artificial intelligence algorithm.
The method of claim 1,
The interview service providing server,
When the expected answer keyword is input when receiving a question from the job search terminal, and the similarity between the text input in the job search terminal and the expected answer keyword exceeds a preset reference value, the percentage of the similarity is extracted to obtain the expected interview score Non-face-to-face online interview service providing system, characterized in that it is transmitted to the job search terminal or the job search terminal.

Images